Token导航 LogoToken导航TokenDH.com
开发需要联网github未标认证来源可访问许可证需确认审计未展示

ring%3apre-dev-subtask-creationring%3apre dev 子任务创建

Agent Skill

ring%3apre-dev-subtask-creation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

840

周安装

35

GitHub Stars

180

下载量

280
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ring%3apre-dev-subtask-creation(ring%3apre dev 子任务创建)
来源仓库:https://github.com/lerianstudio/ring
仓库路径:skills/ring%3Apre-dev-subtask-creation
安装命令:
npx skills add https://github.com/lerianstudio/ring --skill ring:pre-dev-subtask-creation
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/lerianstudio/ring --skill ring:pre-dev-subtask-creation

简介

ring%3apre-dev-subtask-creation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 它适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态和协作事项进行整理。
  • 可通过 npx skills add 命令从 GitHub 仓库安装,功能细节需查阅原始文档。
  • 使用前应确认权限、维护状态及是否触发文件读写或网络请求。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Subtask Creation - Bite-Sized, Zero-Context Steps

Overview

Write comprehensive implementation subtasks assuming the engineer has zero context for our codebase. Each subtask breaks down into 2-5 minute steps following RED-GREEN-REFACTOR. Complete code, exact commands, explicit verification. DRY. YAGNI. TDD. Frequent commits.

Save subtasks to: docs/pre-dev/{feature-name}/subtasks/T-[task-id]/ST-[task-id]-[number]-[description].md

Foundational Principle

Every subtask must be completable by anyone with zero context about the system.

Requiring context creates bottlenecks, onboarding friction, and integration failures.

Subtasks answer: Exactly what to create/modify, with complete code and verification. Subtasks never answer: Why the system works this way (context is removed).

Bite-Sized Step Granularity

Each step is one action (2-5 minutes):

  • "Write the failing test" - step
  • "Run it to make sure it fails" - step
  • "Implement the minimal code to make the test pass" - step
  • "Run the tests and make sure they pass" - step
  • "Commit" - step

Subtask Document Structure

Header (required):

FieldContent
Title# ST-[task-id]-[number]: [Subtask Name]
Agent Note> **For Agents:** REQUIRED SUB-SKILL: Use ring:executing-plans
GoalOne sentence describing what this builds
PrerequisitesVerification commands with expected output
FilesCreate: exact/path, Modify: exact/path:lines, Test: tests/path

Step Structure (TDD Cycle):

StepContent
Step 1: Write failing testComplete test file with imports
Step 2: Run test to verify failCommand + expected failure output
Step 3: Write minimal implementationComplete implementation file
Step 4: Run test to verify passCommand + expected success output
Step 5: Update exports (if needed)Exact modification to index files
Step 6: Verify type checkingCommand + expected output
Step 7: CommitExact git commands with message
RollbackExact commands to undo if issues

Explicit Rules

✅ DO Include in Subtasks

Exact file paths (absolute or from root), complete file contents (if creating), complete code snippets (if modifying), all imports and dependencies, step-by-step TDD cycle (numbered), verification commands (copy-pasteable), expected output (exact), rollback procedures (exact commands), prerequisites (what must exist first)

❌ NEVER Include in Subtasks

Placeholders: "...", "TODO", "implement here"; vague instructions: "update the service", "add validation"; assumptions: "assuming setup is done"; context requirements: "you need to understand X first"; incomplete code: "add the rest yourself"; missing imports: "import necessary packages"; undefined success: "make sure it works"; no verification: "test it manually"

<cannot_skip>

⛔ HARD GATE: lib-commons in Go Code Examples

MUST: For Go projects, code examples use lib-commons instead of custom utilities.

See shared-patterns/code-example-standards.md for:

  • Complete list of what lib-commons provides
  • Forbidden patterns (custom loggers, config loaders, HTTP helpers)
  • Correct import patterns with lib prefix aliases
  • Anti-rationalization table

Quick Reference - DO NOT Create Custom:

CategoryUse lib-commons
LogginglibLog "github.com/LerianStudio/lib-commons/v2/commons/log"
ConfiglibCommons.SetConfigFromEnvVars()
HTTPlibHTTP "github.com/LerianStudio/lib-commons/v2/commons/net/http"
TelemetrylibOpentelemetry "github.com/LerianStudio/lib-commons/v2/commons/opentelemetry"
PostgreSQLlibPostgres "github.com/LerianStudio/lib-commons/v2/commons/postgres"

MUST NOT: Create custom logger, config loader, or HTTP helper in subtasks—use lib-commons.

</cannot_skip>

Rationalization Table

ExcuseReality
"The developer will figure out imports"Imports are context. Provide them explicitly.
"TODO comments are fine for simple parts"TODOs require decisions. Make them now.
"They'll know which service to update"They won't. Specify the exact file path.
"The verification steps are obvious"Obvious ≠ documented. Write exact commands.
"Rollback isn't needed for simple changes"Simple changes fail too. Always provide rollback.
"This needs system understanding"Then you haven't removed context. Simplify more.
"I'll provide the template, they fill it"Templates are incomplete. Provide full code.
"The subtask description explains it"Descriptions need interpretation. Give exact steps.
"They can look at similar code for reference"That's context. Make subtask self-contained.
"This is too detailed, we're not that formal"Detailed = parallelizable = faster. Be detailed.
"Steps are too small, feels like hand-holding"Small steps = verifiable progress. Stay small.
"Custom logger is simpler for this example"Examples teach patterns. Teach lib-commons.
"lib-commons import is too verbose"Verbosity shows correct dependencies. Keep it.
"I'll use lib-commons in the real code"Subtask is real code. Use lib-commons now.

Red Flags - STOP

If you catch yourself writing any of these in a subtask, STOP and rewrite:

  • Code placeholders: ..., // TODO, // implement X here
  • Vague file references: "the user service", "the auth module"
  • Assumption phrases: "assuming you have", "make sure you"
  • Incomplete imports: "import required packages"
  • Missing paths: Not specifying where files go
  • Undefined verification: "test that it works"
  • Steps longer than 5 minutes
  • Context dependencies: "you need to understand X"
  • No TDD cycle in implementation steps
  • Use libZap.NewLogger() instead of custom func NewLogger() (Go)
  • Use libCommons.SetConfigFromEnvVars() instead of scattered os.Getenv() (Go)
  • Use libHTTP utilities instead of custom func JSONResponse() (Go)
  • Check lib-commons first before creating files in utils/, helpers/, pkg/common/ (Go)

When you catch yourself: Expand the subtask until it's completely self-contained.

Gate 8 Validation Checklist

CategoryRequirements
AtomicityEach step 2-5 minutes; no system architecture understanding required; assignable to anyone
CompletenessAll code provided in full; all file paths explicit; all imports listed; all prerequisites documented; TDD cycle followed
VerifiabilityTest commands copy-pasteable; expected output exact; commands run from project root
ReversibilityRollback commands provided; rollback doesn't require system knowledge

Gate Result: ✅ PASS → Ready for implementation | ⚠️ CONDITIONAL (add details) | ❌ FAIL (decompose further)

Confidence Scoring

FactorPointsCriteria
Step Atomicity0-30All 2-5 minutes: 30, Most sized right: 20, Too large/vague: 10
Code Completeness0-30Zero placeholders: 30, Mostly complete: 15, Significant TODOs: 5
Context Independence0-25Anyone can execute: 25, Minor context: 15, Significant knowledge: 5
TDD Coverage0-15All RED-GREEN-REFACTOR: 15, Most have tests: 10, Limited: 5

Action: 80+ autonomous | 50-79 present options | <50 ask about structure

Execution Handoff

After creating subtasks, offer execution choice:

"Subtasks complete. Two execution options:

  1. Subagent-Driven - Fresh subagent per subtask, review between, fast iteration → Use ring:subagent-driven-development
  2. Parallel Session - New session with ring:executing-plans, batch with checkpoints → Use ring:executing-plans

Which approach?"

The Bottom Line

If you wrote a subtask with "TODO" or "..." or "add necessary imports", delete it and rewrite with complete code.

Subtasks are not instructions. Subtasks are complete, copy-pasteable implementations following TDD.

  • "Add validation" is not a step. [Complete validation code with test] is a step.
  • "Update the service" is not a step. [Exact file path + exact code changes with test] is a step.
  • "Import necessary packages" is not a step. [Complete list of imports] is a step.

Every subtask must be completable by someone who:

  • Just joined the team yesterday
  • Has never seen the codebase before
  • Doesn't know the business domain
  • Won't ask questions (you're unavailable)
  • Follows TDD religiously

If they can't complete it with zero questions while following RED-GREEN-REFACTOR, it's not atomic enough.

Remember: DRY. YAGNI. TDD. Frequent commits.


Standards Loading (MANDATORY)

This skill creates implementation subtasks. While it does NOT require direct WebFetch of standards, subtasks MUST reference lib-commons patterns for Go projects.

For Go projects: All code examples in subtasks MUST use lib-commons imports. See shared-patterns/code-example-standards.md for required patterns.

HARD GATE: Subtasks with custom logger, config loader, or HTTP helper implementations are INVALID. Use lib-commons.


Blocker Criteria - STOP and Report

ConditionActionSeverity
Tasks (Gate 7) not validatedSTOP and complete Gate 7 firstCRITICAL
Subtask contains TODO or placeholderSTOP and expand with complete codeHIGH
Subtask requires context not providedSTOP and add missing context to subtaskHIGH
Step exceeds 5 minutesSTOP and break into smaller stepsMEDIUM
Missing TDD cycle (no RED phase)STOP and add failing test firstHIGH
Go subtask uses custom logger instead of lib-commonsSTOP and replace with lib-commonsHIGH

Cannot Be Overridden

These requirements are NON-NEGOTIABLE:

  • MUST NOT include placeholders (TODO,..., "implement here")
  • MUST NOT include vague instructions ("update the service")
  • MUST provide complete file paths (absolute or from root)
  • MUST provide all imports explicitly
  • MUST follow TDD cycle: RED (failing test) → GREEN (implementation) → REFACTOR
  • MUST include verification commands with expected output
  • MUST include rollback procedures
  • MUST use lib-commons for Go code examples (no custom utilities)

Severity Calibration

SeverityDefinitionExample
CRITICALSubtask cannot be executedMissing prerequisite, no file paths
HIGHSubtask requires interpretationTODO placeholder, vague description
MEDIUMSubtask quality degradedMissing verification command
LOWMinor documentation gapsRollback could be more detailed

Pressure Resistance

User SaysYour Response
"Developer will figure out imports""Cannot assume imports. Imports ARE context. I'll provide explicit import statements."
"TODO comments are fine for simple parts""Cannot use TODOs. TODOs require decisions. I'll make those decisions now and provide complete code."
"Steps are too detailed, feels like hand-holding""Cannot reduce detail. Small steps = verifiable progress. Detail enables parallelization."
"Skip TDD for this simple change""Cannot skip TDD. Every subtask follows RED-GREEN-REFACTOR. I'll write the failing test first."
"Custom logger is simpler for this example""Cannot use custom logger. Subtasks teach patterns. lib-commons is the pattern."

When This Skill Is Not Needed

  • Small Track workflow (execute tasks directly without subtask breakdown)
  • Tasks are simple enough without fine-grained breakdown
  • Tasks (Gate 7) not yet validated (complete Gate 7 first)
  • Implementation already in progress (use ring:executing-plans)
  • Proof-of-concept work without formal process needs

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.61%
按下载量换算100

Claude

32.21%
按下载量换算90

Cursor

19.56%
按下载量换算55

Gemini CLI

10.1%
按下载量换算28

安全审计

暂无安全审计结果可展示。

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills